INDEX

Explanations

references to legends and myths

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hoeddwyd

-0.83

ędzy

-0.79

zzleHttp

-0.78

Twee

-0.77

 sputnik

-0.76

ędzynarod

-0.75

Ril

-0.73

moiselle

-0.73

oarece

-0.72

 Sputnik

-0.72

POSITIVE LOGITS

legend

2.22

 Legend

2.15

 legend

2.12

 legends

1.99

Legend

1.95

 Legends

1.93

 LEGEND

1.89

Legends

1.69

LEGEND

1.68

legends

1.59

Activations Density 0.048%

references to legends and myths

No Comments

No Known Activations